Clayton Sanford

25 papers A* 8Journal 17
YearRankTypeTitle / Venue / Authors
2026 J jnl
Next-Token Prediction and Regret Minimization.
CoRR
Mehryar Mohri, Clayton Sanford, Jon Schneider, Kiran Vodrahalli, Yifan Wu
2025 A* conf
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models.
ICML
Ali Behrouz, Ali Parviz, Mahdi Karami, Clayton Sanford, Bryan Perozzi, Vahab Mirrokni
2025 J jnl
Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers.
CoRR
Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson
2025 J jnl
Fast attention mechanisms: a tale of parallelism.
CoRR
Jingwen Liu, Hantao Yu, Clayton Sanford, Alexandr Andoni, Daniel Hsu
2025 J jnl
When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective.
CoRR
Alireza Mousavi Hosseini, Clayton Sanford, Denny Wu, Murat A. Erdogdu
2024 J jnl
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models.
CoRR
Ali Behrouz, Ali Parviz, Mahdi Karami, Clayton Sanford, Bryan Perozzi, Vahab Mirrokni
2024 J jnl
One-layer transformers fail to solve the induction heads task.
CoRR
Clayton Sanford, Daniel Hsu, Matus Telgarsky
2024 A* conf
Transformers, parallel computation, and logarithmic depth.
ICML
Clayton Sanford, Daniel Hsu, Matus Telgarsky
2024 J jnl
Transformers, parallel computation, and logarithmic depth.
CoRR
Clayton Sanford, Daniel Hsu, Matus Telgarsky
2024 A* conf
Understanding Transformer Reasoning Capabilities via Graph Algorithms.
NeurIPS
Clayton Sanford, Bahare Fatemi, Ethan Hall, Anton Tsitsulin, Mehran Kazemi, Jonathan Halcrow, Bryan Perozzi, Vahab Mirrokni
2024 J jnl
Understanding Transformer Reasoning Capabilities via Graph Algorithms.
CoRR
Clayton Sanford, Bahare Fatemi, Ethan Hall, Anton Tsitsulin, Seyed Mehran Kazemi, Jonathan Halcrow, Bryan Perozzi, Vahab Mirrokni
2023 A* conf
Representational Strengths and Limitations of Transformers.
NeurIPS
Clayton Sanford, Daniel J. Hsu, Matus Telgarsky
2023 J jnl
Representational Strengths and Limitations of Transformers.
CoRR
Clayton Sanford, Daniel Hsu, Matus Telgarsky
2022 J jnl
Intrinsic dimensionality and generalization properties of the R-norm inductive bias.
CoRR
Clayton Sanford, Navid Ardeshir, Daniel Hsu
2022 J jnl
Learning Single-Index Models with Shallow Neural Networks.
CoRR
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
2022 A* conf
Learning single-index models with shallow neural networks.
NeurIPS
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
2022 J jnl
Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals.
CoRR
Daniel Hsu, Clayton Sanford, Rocco A. Servedio, Emmanouil V. Vlatakis-Gkaragkounis
2022 A* conf
On Scrambling Phenomena for Randomly Initialized Recurrent Networks.
NeurIPS
Vaggos Chatziafratis, Ioannis Panageas, Clayton Sanford, Stelios Stavroulakis
2022 J jnl
On Scrambling Phenomena for Randomly Initialized Recurrent Networks.
CoRR
Vaggos Chatziafratis, Ioannis Panageas, Clayton Sanford, Stelios Andrew Stavroulakis
2021 J jnl
Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem.
CoRR
Clayton Sanford, Vaggos Chatziafratis
2021 A* conf
On the Approximation Power of Two-Layer Networks of Random ReLUs.
COLT
Daniel Hsu, Clayton Sanford, Rocco A. Servedio, Emmanouil V. Vlatakis-Gkaragkounis
2021 J jnl
On the Approximation Power of Two-Layer Networks of Random ReLUs.
CoRR
Daniel Hsu, Clayton Sanford, Rocco A. Servedio, Emmanouil V. Vlatakis-Gkaragkounis
2021 A* conf
Support vector machines and linear regression coincide with very high-dimensional features.
NeurIPS
Navid Ardeshir, Clayton Sanford, Daniel J. Hsu
2021 J jnl
Support vector machines and linear regression coincide with very high-dimensional features.
CoRR
Navid Ardeshir, Clayton Sanford, Daniel Hsu
2018 J jnl
Uniform Convergence Bounds for Codec Selection.
CoRR
Clayton Sanford, Cyrus Cousins, Eli Upfal